Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 56145
    Prev
    Next
    INDEX
    Explanations

    numerical references or identifiers in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    conomy
    -0.07
    letal
    -0.07
    ermann
    -0.06
     ÄĮer
    -0.06
    meli
    -0.06
     Economy
    -0.06
    /libs
    -0.06
    Ñŀ
    -0.06
    940
    -0.06
    ÑĥÑĩ
    -0.06
    POSITIVE LOGITS
     Mage
    0.07
    olu
    0.07
    leftright
    0.07
    Formatting
    0.06
    attend
    0.06
    erez
    0.06
     bust
    0.06
     McCabe
    0.06
     Verfüg
    0.06
    окÑĥ
    0.06
    Activations Density 0.001%

    No Known Activations